Model save

README.md

@@ -0,0 +1,59 @@
+---
+license: llama2
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: meta-llama/LlamaGuard-7b
+model-index:
+- name: llama-guard-finetuned-3ep-800
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama-guard-finetuned-3ep-800
+
+This model is a fine-tuned version of [meta-llama/LlamaGuard-7b](https://huggingface.co/meta-llama/LlamaGuard-7b) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 0.6
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.39.3
+- Pytorch 2.3.0+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c1cb43153ab29864cf163317bca7cb846a8b46ee69b9afb90b5c74709b5fd9
+oid sha256:cec974c9e18c872daa55cbf65fc9f49aa3411d81e8fdf66ba44a636928835906
 size 1182844512

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.6,
+    "total_flos": 9030484680671232.0,
+    "train_loss": 0.566877440582934,
+    "train_runtime": 2411.1952,
+    "train_samples": 1851,
+    "train_samples_per_second": 0.461,
+    "train_steps_per_second": 0.058
+}

runs/Apr09_23-37-16_llamaguard2/events.out.tfevents.1712705843.llamaguard2.14510.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e80acec57552484f28cff2a69b4092c769ec4c509181621c77ccf90238960b
-size 6149
+oid sha256:2df8a4587662dad82d1e8e9073e5dccd01340f33fb43bdddbd25f00e7771b2d2
+size 6503

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.6,
+    "total_flos": 9030484680671232.0,
+    "train_loss": 0.566877440582934,
+    "train_runtime": 2411.1952,
+    "train_samples": 1851,
+    "train_samples_per_second": 0.461,
+    "train_steps_per_second": 0.058
+}

trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6004319654427646,
+  "eval_steps": 500,
+  "global_step": 139,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.675453782081604,
+      "learning_rate": 0.0002,
+      "loss": 2.08,
+      "step": 25
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.3721127510070801,
+      "learning_rate": 0.0002,
+      "loss": 0.3546,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.161994069814682,
+      "learning_rate": 0.0002,
+      "loss": 0.2689,
+      "step": 75
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.08174678683280945,
+      "learning_rate": 0.0002,
+      "loss": 0.1425,
+      "step": 100
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.1015535444021225,
+      "learning_rate": 0.0002,
+      "loss": 0.2211,
+      "step": 125
+    },
+    {
+      "epoch": 0.6,
+      "step": 139,
+      "total_flos": 9030484680671232.0,
+      "train_loss": 0.566877440582934,
+      "train_runtime": 2411.1952,
+      "train_samples_per_second": 0.461,
+      "train_steps_per_second": 0.058
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 139,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 9030484680671232.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}